基于支持向量机的GNSS时间序列预测

在深度学习的理论框架下,针对预测全球卫星导航系统(GNSS)时间序列,传统的经验风险最小化预测模型误差大精度低,泛化性能差且对历史数据的经验依赖大的问题.提出一种采用结构风险最小化原则的基于支持向量机(SVM)的时间序列预测模型.通过和多层的BP神经网络预测模型预测效果比较,结果证明SVM预测模型拥有更好的时间序列预测效果.

GNSS time series prediction based on support vector machine

In order to predict the global navigation satellite system (GNSS) time series, under the theoretical framework of deep learning, the traditional empirical risk minimization prediction model has low error, low generalization performance and large dependence on historical data. A time series prediction model is proposed based on support vector machine (SVM) with the principle of structural risk minimization. compared with the multi-layer BP neural network prediction model prediction, the results prove that the SVM prediction model has better time series prediction effect.